#### Filter Results:

- Full text PDF available (38)

#### Publication Year

1985

2009

- This year (0)
- Last 5 years (0)
- Last 10 years (6)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

- Andreas Stolcke, Stephen M. Omohundro
- ICGI
- 1994

We describe a framework for inducing probabilistic grammars from corpora of positive samples. First, samples are incorporated by adding ad-hoc rules to a working grammar; subsequently, elements of the model (such as states or nonterminals) are merged to achieve generalization and a more compact representation. The choice of what to merge and when to stop is… (More)

This paper describes PicHunter, an image retrieval sys tem that implements a novel approach to relevance feedback. It uses Bayesian learning based on a probabilistic model of a user's behavior. The predictions of this model are com bined with the selections made during a search to choose the images to display. The details of our model were tuned using an… (More)

- Andreas Stolcke, Stephen M. Omohundro
- NIPS
- 1992

This paper describes a technique for learning both the number of states and the topology of Hidden Markov Models from examples. The induction process starts with the most specific model consistent with the training data and generalizes by successively merging states. Both the choice of states to merge and the stopping criterion are guided by the Bayesian… (More)

- Andreas Stolcke, Stephen M. Omohundro
- ArXiv
- 1994

This report describes a new technique for inducing the structure of Hidden Markov Models from data which is based on the general 'model merging' strategy (Omohundro 1992). The process begins with a maximum likelihood HMM that directly encodes the training data.' Successively more general models are produced by merging HMM states. A Bayesian posterior… (More)

- Stephen M. Omohundro
- AGI
- 2008

One might imagine that AI systems with harmless goals will be harmless. This paper instead shows that intelligent systems will need to be carefully designed to prevent them from behaving in harmful ways. We identify a number of “drives” that will appear in sufficiently advanced AI systems of any design. We call them drives because they are tendencies which… (More)

- Stephen M. Omohundro
- Complex Systems
- 1987

This paper addresses how the effectiveness of a content based, multimedia information retrieval system can be mea sured, and how such a system should best use response feed back in performing searches. We propose a simple, quan tifiable measure of an image retrieval system's effective ness, "target testing", in which effectiveness is measured as the… (More)

- Clemens A. Szyperski, Stephen M. Omohundro, Stephan Murer
- Programming Languages and System Architectures
- 1994

ion de ned by that type. With multi-methods code does not naturally belong to a particular type. Sather deals with multi-method situations by using \typecase" statements. These appear in the body of a routine which dispatches on the rst argument type and may explicitly dispatch on the second argument type. Unlike a simple \case" statement applied to the… (More)

- Christoph Bregler, Stephen M. Omohundro
- ICCV
- 1995

A technique for representing and learning smooth nonlinear manifolds is presented and applied to sev eral lip reading tasks. Given a set of points drawn from a smooth manifold in an abstract feature space, the technique is capable of determining the structure of the surface and of finding the closest manifold point to a given query point. We use this… (More)

- Christoph Bregler, Stephen M. Omohundro
- NIPS
- 1993

Most connectionist research has focused on learning mappings from one space to another (eg. classification and regression). This paper introduces the more general task of learning constraint surfaces. It describes a simple but powerful architecture for learning and manipulating nonlinear surfaces from data. We demonstrate the technique on low dimensional… (More)